Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Role of tyrosinase in ocular growth and myopia development in a guinea pig model.

Scientific reports·2026
Same author

Tanshinone IIA inhibits choroidal neovascularization and restores outer blood-retinal barrier function in Vldlr knockout mice.

Experimental eye research·2026
Same author

Placental DNA methylation as a mediator in the association between maternal prenatal bisphenol analogue exposure and myopia in children: A long-term prospective cohort study.

Environmental research·2026
Same author

SpineVLM: A Markdown-Guided Structured Fine-Tuning Framework for Spine X-ray Report Generation.

IEEE journal of biomedical and health informatics·2026
Same author

The role of circadian rhythms in the pathogenesis of myopia.

Frontiers in physiology·2026
Same author

CPNE1: A novel therapeutic target for myopia progression - from genetic GWAS discovery to functional validation in vitro and vivo.

Journal of translational medicine·2026

相关实验视频

Updated: Jan 13, 2026

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies
06:16

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

3.0K

视网膜特征作为高近视的预测指标:可解释的多机器学习模型的见解.

Haohan Zou1,2,3, Jing Liu4, Shenda Shi5

  • 1Tianjin Eye Hospital, Tianjin, China.

Frontiers in bioengineering and biotechnology
|October 29, 2025
PubMed
概括

机器学习模型可以使用视网膜特征预测高近视 (HM). 关键因素包括形密度和血管参数,具体的值表明风险.

关键词:
深度学习是一种深度学习.高近视的高近视是一个问题.机器学习是机器学习.视网膜成像 omics 的成像沙普利添加剂 扩展 扩展 扩展

更多相关视频

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
Inducement and Evaluation of a Murine Model of Experimental Myopia
07:20

Inducement and Evaluation of a Murine Model of Experimental Myopia

Published on: January 22, 2019

10.4K

相关实验视频

Last Updated: Jan 13, 2026

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies
06:16

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

3.0K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
Inducement and Evaluation of a Murine Model of Experimental Myopia
07:20

Inducement and Evaluation of a Murine Model of Experimental Myopia

Published on: January 22, 2019

10.4K

科学领域:

  • 眼科医生 眼科 眼科
  • 医疗成像医学成像
  • 机器学习 机器学习

背景情况:

  • 高近视 (HM) 构成对视力威胁状况的重大风险.
  • 准确预测HM对于早期干预和管理至关重要.
  • 视网膜结构特征越来越多地被认为是HM的潜在生物标志物.

研究的目的:

  • 评估多个机器学习 (ML) 算法在基于视网膜特征的高近视 (HM) 预测方面的有效性.
  • 开发一个可解释的框架,以了解视网膜参数对HM预测的贡献.

主要方法:

  • 使用深度语义细分网络,从2981名患者的眼睛 (1191名HM,1790名非HM) 中提取了定量视网膜结构参数.
  • 训练了五种不同的ML算法,并对其预测性能进行了评估.
  • 使用夏普利添加式解释 (SHAP) 方法分析特征重要性和模型可解释性.

主要成果:

  • 极端梯度增强 (XGBoost) 模型表现出卓越的性能,达到0.81的精度和0.87.87的AUC.
  • 鉴定出了12个关键特征,包括形密度,血管参数,副形缩特征和光盘测量.
  • 特定的形密度,帕拉帕皮拉底缩宽度/面积和各种血管/光盘参数的具体值与增加或减少HM风险有关.

结论:

  • 该XGBoost模型,利用视网膜特征,有效地预测高近视.
  • SHAP分析为特定视网膜特征的预测能力提供了关键的见解,提高了临床适用性.